Vector search
C-84Similar resolved case
Damaged parcel → photo reviewed → replacement approved.
All industries Give every agent
BPOs & contact centres
Give every agent
the right context.
Bring customer records, relevant cases, and searchable knowledge into the support applications your agents use.
From a question to its sources
Put the evidence beside the answer.
Your application retrieves authorized context, assembles the sources, and presents a draft for a human agent to review.
01 / Customer contextSQL
The current case
- Order
- O-52
- Delivery
- Received
- Issue
- Damaged item
- Access
- Assigned agent
Read only the records this agent is allowed to see.
02 / Retrieve knowledge
Related, with a source
Full-text search
K-12Exact policy passage
“Request a photo of the damaged item before reviewing a replacement.”
03 / Application draft
Ready for review
“Please share a photo of the damaged item so we can review a replacement.”
Policy source
K-12The agent checks the policy and customer details before sending.
Awaiting human review
Application boundary
Authorize access → retrieve records and passages → assemble context → generate a draft with your model → human review.
OriginChainDB supplies the records and retrieval queries. Your application owns model calls, source references, workflow decisions, and the response sent to the customer.
Explore grounded retrieval5 use cases / Contact centres
The right modalities for your workflow.
Start with the combination that fits your question. These are recommended starting points; the best fit depends on your data and query patterns.
- SQL Filter, join and aggregate records
- Graph Follow relationships between records
- FTS · Full-text search Find keywords, phrases and exact wording
- Vector Find similar items or meaning
| Use case | Recommended modalities | Why this combination fits |
|---|---|---|
| Agent knowledge assistance Retrieve useful knowledge passages for the current customer question. | SQL supplies customer and case context, FTS matches exact terms, and Vector finds guidance phrased differently from the question. | |
| Customer journey context Connect conversations, cases and service relationships. | SQL retrieves customer attributes and interaction dates. Graph follows the links between customers, conversations and cases. | |
| Escalation evidence review Follow an escalated case through related conversations and documents. | SQL supplies case status, Graph connects the related interactions, and FTS finds promises, issue terms and quoted language. | |
| Conversation quality review Find conversations containing phrases that a reviewer needs to inspect. | SQL selects queues, teams and date ranges. FTS finds matching phrases in indexed transcripts for manual review. | |
| Queue and workload reporting Track case volumes, assignments and resolution times. | SQL groups operational records by team, queue and period, with filters for status and assignment. |
Combine query results in your application using shared record IDs. Keep text indexes and embeddings updated as the source data changes.
Build one assistance path first
Start with the knowledge your agents trust.
Use a reviewed set of support questions to check retrieval, permissions, and source freshness before broadening the workflow.
Follow the RAG guideModel cases and source passages.
Keep stable IDs for cases, documents, and chunks. Store policy versions alongside the text so your application can show which source it used.
Define the recordsKeep retrieval in step with changes.
Write rows, vectors, and full-text entries through separate calls. Re-embed and re-index revised policies; test retries and removal of retired passages.
Set up semantic retrievalTest boundaries and missing answers.
Verify programme isolation and agent permissions. When the available sources do not support a reply, have your application request clarification or escalate.
Review access controlsBuilt around your service workflow